Developed QSAR Models Research Articles

Modelling Inhalational Anaesthetics Using Bayesian Feature Selection and QSAR Modelling Methods

The development of robust and predictive QSAR models is highly dependent on the use of molecular descriptors that contain information relevant to the property being modelled. Selection of these relevant features from a large pool of possibilities is difficult to achieve effectively. Modern Bayesian methods provide substantial advantages over conventional feature selection methods for feature selection and QSAR modelling. We illustrate the importance of descriptor choice and the beneficial properties of Bayesian methods to select context-dependent relevant descriptors and build robust QSAR models, using data on anaesthetics. Our results show the effectiveness of Bayesian feature selection methods in choosing the best descriptors when these are mixed with less informative descriptors. They also demonstrate the efficacy of the Abraham descriptors and identify deficiencies in ParaSurf descriptors for modelling anaesthetic action.

Best Practices for QSAR Model Development, Validation, and Exploitation.

After nearly five decades "in the making", QSAR modeling has established itself as one of the major computational molecular modeling methodologies. As any mature research discipline, QSAR modeling can be characterized by a collection of well defined protocols and procedures that enable the expert application of the method for exploring and exploiting ever growing collections of biologically active chemical compounds. This review examines most critical QSAR modeling routines that we regard as best practices in the field. We discuss these procedures in the context of integrative predictive QSAR modeling workflow that is focused on achieving models of the highest statistical rigor and external predictive power. Specific elements of the workflow consist of data preparation including chemical structure (and when possible, associated biological data) curation, outlier detection, dataset balancing, and model validation. We especially emphasize procedures used to validate models, both internally and externally, as well as the need to define model applicability domains that should be used when models are employed for the prediction of external compounds or compound libraries. Finally, we present several examples of successful applications of QSAR models for virtual screening to identify experimentally confirmed hits.

Global QSAR models of skin sensitisers for regulatory purposes

BackgroundThe new European Regulation on chemical safety, REACH, (Registration, Evaluation, Authorisation and Restriction of CHemical substances), is in the process of being implemented. Many chemicals used in industry require additional testing to comply with the REACH regulations. At the same time EU member states are attempting to reduce the number of animals used in experiments under the 3 Rs policy, (refining, reducing, and replacing the use of animals in laboratory procedures). Computational techniques such as QSAR have the potential to offer an alternative for generating REACH data. The FP6 project CAESAR was aimed at developing QSAR models for 5 key toxicological endpoints of which skin sensitisation was one.ResultsThis paper reports the development of two global QSAR models using two different computational approaches, which contribute to the hybrid model freely available online.ConclusionsThe QSAR models for assessing skin sensitisation have been developed and tested under stringent quality criteria to fulfil the principles laid down by the OECD. The final models, accessible from CAESAR website, offer a robust and reliable method of assessing skin sensitisation for regulatory use.

Per Aspera Ad Astra : Application of Simplex Qsar Approach in Antiviral Research

This review explores the application of the Simplex representation of molecular structure (SiRMS) QSAR approach in antiviral research. We provide an introduction to and description of SiRMS, its application in antiviral research and future directions of development of the Simplex approach and the whole QSAR field. In the Simplex approach every molecule is represented as a system of different simplexes (tetratomic fragments with fixed composition, structure, chirality and symmetry). The main advantages of SiRMS are consideration of the different physical-chemical properties of atoms, high adequacy and good interpretability of models obtained and clear procedures for molecular design. The reliability of developed QSAR models as predictive virtual screening tools and their ability to serve as the basis of directed drug design was validated by subsequent synthetic and biological experiments. The SiRMS approach is realized as the complex of the computer program 'HiT QSAR', which is available on request.

Trust, But Verify: On the Importance of Chemical Structure Curation in Cheminformatics and QSAR Modeling Research

Molecular modelers and cheminformaticians typically analyze experimental data generated by other scientists. Consequently, when it comes to data accuracy, cheminformaticians are always at the mercy of data providers who may inadvertently publish (partially) erroneous data. Thus, dataset curation is crucial for any cheminformatics analysis such as similarity searching, clustering, QSAR modeling, virtual screening, etc., especially nowadays when the availability of chemical datasets in public domain has skyrocketed in recent years. Despite the obvious importance of this preliminary step in the computational analysis of any dataset, there appears to be no commonly accepted guidance or set of procedures for chemical data curation. The main objective of this paper is to emphasize the need for a standardized chemical data curation strategy that should be followed at the onset of any molecular modeling investigation. Herein, we discuss several simple but important steps for cleaning chemical records in a database including the removal of a fraction of the data that cannot be appropriately handled by conventional cheminformatics techniques. Such steps include the removal of inorganic and organometallic compounds, counterions, salts and mixtures; structure validation; ring aromatization; normalization of specific chemotypes; curation of tautomeric forms; and the deletion of duplicates. To emphasize the importance of data curation as a mandatory step in data analysis, we discuss several case studies where chemical curation of the original “raw” database enabled the successful modeling study (specifically, QSAR analysis) or resulted in a significant improvement of model's prediction accuracy. We also demonstrate that in some cases rigorously developed QSAR models could be even used to correct erroneous biological data associated with chemical compounds. We believe that good practices for curation of chemical records outlined in this paper will be of value to all scientists working in the fields of molecular modeling, cheminformatics, and QSAR studies.

Development of a mechanistic QSAR model for the detection of phototoxic chemicals and use in an integrated testing strategy

Development of a mechanistic QSAR model for the detection of phototoxic chemicals and use in an integrated testing strategy

Prediction of highly-connected 'hub'-proteins in protein interaction networks using QSAR

Proteins that are most essential for functioning and viability of bacterial cell have been shown to exhibit larger number of interactions with other cell components. Thus, by identifying the most connected proteins (or hubs) in protein interaction networks (PINs), one may discover prospective drug targets that can be utilized to combat emergent and drug-resistant pathogens such as Methicillin-Resistant Staphylococcus aureus 252 (MRSA). The advantage of using such hub proteins as drug targets lies in their essentiality, non-replaceable position in the PIN and lower rate of mutation, which can help to counter bacterial resistance. However, finding or predicting such hub proteins remains a challenging task as the corresponding experiments are very costly, while traditional bioinformatics approaches generally fail in forecasting PIN data due to the general lack of agreement between the existing datasets [1]. Thus, we have decided to utilize various structural and physicochemical features of proteins, related to traditional QSAR properties for predicting highly connected proteins. Using our own in-house generated PIN for the MRSA cell we have trained a boosting tree-based classifier that uses 75 physical and chemical QSAR descriptors computed for all proteins in the interaction network [2]. The utilized parameters included molecular weight, net charge, isoelectric point, hydrophobicity, surface area, solvent accessibilities, electronegativity, secondary structure composition, surface coils and flexibility among other QSAR descriptors. The developed QSAR model has yielded a high prediction accuracy of 80% for the validation set and was used to predict additional hubs in the rest of the MRSA proteome. The predicted hubs have then been evaluated experimentally and 55% of them were confirmed as high interactors what corresponds to >5 fold dataset enrichment for potential hub-proteins provided by the developed QSAR model. Thus, the successful development of accurate hub classifiers demonstrated that highly-connected proteins tend to share certain structural and physicochemical features that can be characterized and quantified by conventional QSAR descriptors. It is anticipated that the developed hub classifiers will represent a useful tool for the prediction of highly-interacting proteins and can find broad application for planning and executing large-scale proteomic experiments and for identification of novel and prospective antibacterial drug targets – even in those organisms that currently lack protein interaction data.

QSAR Analysis of Poliovirus Inhibition By Dual Combinations of Antivirals

We have applied Hierarchical QSAR Tech- nology (HiT QSAR) to the prediction of antiviral effects of paired combinations of picornavirus replication inhibitors against poliovirus 1 (Mahoney) in vitro. The inhibition from all binary combinations of eight antivirals were investigated. Simplex representation of molecular structure (SiRMS) was used for the generation of molecular descriptors of both pure compounds and all dual mixture combinations. Predictive QSAR models were obtained using the partial least squares (PLS) method. Predictive power of the developed models was validated using eightfold external cross-validation (CV, Q 2 = 0.67-0.93). Adequate models (Q 2 = 0.53-0.97) were obtained in the same way for predicting measured inhibitory concentra- tions at other levels (i.e., IC30 ,I C 40 ,I C 60 ,I C 70). The usage of predicted values of these concentrations in the frame- work of the feature net (FN) approach led to an insignifi- cant increase in the quality of the obtained QSAR models (Q 2 = 0.71-0.94). Developed QSAR models were ana- lyzed and interpreted so that structural fragments and components of the combination promoting the antiviral activity were determined (e.g., 2-(4-methoxyphenyl)-4,5- dihydrooxazole or the combination of N-hydroxybenzimi- doyl and 3-methylisoxasole). Then the resulting consensus model was used to predict novel potent combinations of drugs. Combinations of enviroxime with pleconaril, WIN52084, and rupintrivir and the mixture of rupintrivir with disoxaril were predicted to cause the most inhibition of poliovirus 1 replication. HiT QSAR proved itself as an adequate tool for QSAR analysis of mixtures and, although the method described here is suitable only for binary mixtures, it can be easily extended for more complex combinations.

Classical and 3D-QSAR studies of cytochrome 17 inhibitor imidazole-substituted biphenyls

Classical and 3D-quantitative structure–activity relationship (3D-QSAR) studies have been performed for a series of imidazole-substituted biphenyl derivatives (n = 28) having 17α-hydroxylase/17-20-lyase (CYP17) inhibitory activity. 3D-QSAR analyses were performed using molecular shape analysis (MSA), receptor surface analysis (RSA) and molecular field analysis (MFA). The chemometric tools used for the analysis are genetic function approximation (classical QSAR and MSA) and genetic partial least squares (MFA and RSA). The developed QSAR models suggest that the presence of an imidazole group at the para position of the biphenyl ring is favourable for the inhibitory activity. The MSA-derived model indicates the importance of different shadow parameters (Lx, Syz) as well as molecular rigidity. The MFA model suggests the interaction points near the phenyl ring and the imidazole ring, while the RSA model indicates the nature of the hypothetical receptor surface around the ring systems. The RSA-derived model was found to be the best model based on the highest internal (Q 2 = 0.932) predictive power as well as criteria (0.858). According to external prediction statistics ( = 0.876), the MFA-derived model outperforms other models. Overall, there should be small (–H, –OH, –NH2) hydrophilic hydrogen bond donor groups at the terminal phenyl ring (meta or para position) for optimum inhibitory activity.

Docking and 3D-QSAR studies of diverse classes of human aromatase (CYP19) inhibitors

Aromatase (cytochrome 19) inhibitors have emerged as promising candidates for treatment of breast cancer. In search of potent aromatase inhibitors, docking and three-dimensional quantitative structure-activity relationship (3D-QSAR) studies using molecular shape, spatial, electronic, structural and thermodynamic descriptors have been performed on a diverse set of compounds having human aromatase inhibitory activities. An attempt has also been made to include two-dimensional (2D) descriptors in the QSAR studies. The chemometric tools used for model development are genetic function approximation (GFA) and genetic partial least squares (G/PLS). The docking study shows that the important interacting amino acids in the active site cavity are Met374, Arg115, Ile133, Ala306, Thr310, Asp309, Val370 and Ser478. One or more hydrogen bond formation with Met374 is one of the essential requirements for the ligands for optimum aromatase inhibition. The binding is further stabilized by van der Waals interactions with a few non-polar amino acid residues in the active site. The developed QSAR models indicate the importance of different shape, Jurs parameters, structural parameters, topological branching index and E-state index for different fragments. The results obtained from the QSAR analysis are supported by our docking observations. There should be one or two hydrogen bond acceptor groups (like -NO2, -CN) and optimal hydrophobicity for ideal aromatase inhibitors. A GFA model with spline option obtained using 3D descriptors was found to be the best model based on internal validation (Q2=0.668) while the best (externally) predictive model was a GFA model with spline option using combined set (2D and 3D) descriptors (Rpred2=0.687). Based on rm2(overall) criterion, the best model was a G/PLS model (using 3D descriptors) with spline option (rm2(overall)=0.606).

A QSAR Study on the Cytotoxicity of Podophyllotoxin Analogues Against Various Cancer Cell Lines

The powerful inhibitory activity of podophyllotoxin (a natural product) on cell growth led to the development of clinically useful anticancer agents such as etoposide, teniposide, and etopophos. Although, these podophyllotoxin derivatives show good clinical effects against various cancers, its use often results in various undesired side effects, drug resistance, and cytotoxicity towards the normal cells. In order to overcome these limitations, it is essential to search new podophyllotoxin analogues with improved anticancer activity and fewer side effects to gain the maximum benefits for the cancer patients. With this purpose, the cytotoxicity data of two series of podophyllotoxin derivatives against four different cancer cell lines was used to develop 4 QSAR models. Hydrophobic property of the molecules was found one of the most important determining factors for their activity. The developed QSAR models showed a good correlative and predictive abilities having r(2) = 0.960 to 0.836 and q(2) = 0.911 to 0.705. On the basis of QSAR 1, two compounds (10-10 and 10-11) are suggested as potential synthetic targets. Statistical diagnostics and internal validation (cross validation and Y-randomization) tests have validated all the QSAR models. These QSAR models could be useful in the rational design of potential drug molecules with an enhanced inhibitory potency.

Prediction of carcinogenicity for diverse chemicals based on substructure grouping and SVM modeling

The Carcinogenicity Reliability Database (CRDB) was constructed by collecting experimental carcinogenicity data on about 1,500 chemicals from six sources, including IARC, and NTP databases, and then by ranking their reliabilities into six unified categories. A wide variety of 911 organic chemicals were selected from the database for QSAR modeling, and 1,504 kinds of different molecular descriptors were calculated, based on their 3D molecular structures as modeled by the Dragon software. Positive (carcinogenic) and negative (non-carcinogenic) chemicals containing various substructures were counted using atom and functional group count descriptors, and the statistical significance of ratios of positives to negatives was tested for those substructures. Very few were judged to be strongly related to carcinogenicity, among substructures known to be responsible for carcinogens as revealed from biomedical studies. In order to develop QSAR models for the prediction of the carcinogenicities of a wide variety of chemicals with a satisfactory performance level, the relationship between the carcinogenicity data with improved reliability and a subset of significant descriptors selected from 1,504 Dragon descriptors was analyzed with a support vector machine (SVM) method: the classification function (SVC) for weighted data in LIBSVM program was used to classify chemicals into two carcinogenic categories (positive or negative), where weights were set depending on the reliabilities of the carcinogenicity data. The quality and stability of the models presented were tested by performing a dual cross-validation procedure. A single SVM model as the first step was developed for all the 911 chemicals using 250 selected descriptors, achieving an overall accuracy level, i.e., positive and negative correct estimate, of about 70%. In order to improve the accuracy of the final model, the 911 chemicals were classified into 20 mutually overlapping subgroups according to contained substructures, a specific SVM model was optimized for each subgroup, and the predicted carcinogenicities of the 911 chemicals were determined by the majorities of the outputs of the corresponding SVM models. The model developed on the basis of grouping of chemicals into 20 substructures predicts the carcinogenicities of a wide variety of chemicals with a satisfactory overall accuracy of approximately 80%.

3D-Pharmacophore mapping of thymidine-based inhibitors of TMPK as potential antituberculosis agents

Tuberculosis (TB) is the primary cause of mortality among infectious diseases. Mycobacterium tuberculosis monophosphate kinase (TMPKmt) is essential to DNA replication. Thus, this enzyme represents a promising target for developing new drugs against TB. In the present study, the receptor-independent, RI, 4D-QSAR method has been used to develop QSAR models and corresponding 3D-pharmacophores for a set of 81 thymidine analogues, and two corresponding subsets, reported as inhibitors of TMPKmt. The resulting optimized models are not only statistically significant with r(2) ranging from 0.83 to 0.92 and q(2) from 0.78 to 0.88, but also are robustly predictive based on test set predictions. The most and the least potent inhibitors in their respective postulated active conformations, derived from each of the models, were docked in the active site of the TMPKmt crystal structure. There is a solid consistency between the 3D-pharmacophore sites defined by the QSAR models and interactions with binding site residues. Moreover, the QSAR models provide insights regarding a probable mechanism of action of the analogues.

Support vector machines: Development of QSAR models for predicting anti-HIV-1 activity of TIBO derivatives

The tetrahydroimidazo[4,5,1-jk][1,4]benzodiazepinone (TIBO) derivatives, as non-nucleoside reverse transcriptase inhibitors, acquire a significant place in the treatment of the infections by the HIV. In the present paper, the support vector machines (SVM) are used to develop quantitative relationships between the anti-HIV activity and four molecular descriptors of 82 TIBO derivatives. The results obtained by SVM give good statistical results compared to those given by multiple linear regressions and artificial neural networks. The contribution of each descriptor to structure-activity relationships was evaluated. It indicates the importance of the hydrophobic parameter. The proposed method can be successfully used to predict the anti-HIV of TIBO derivatives with only four molecular descriptors which can be calculated directly from molecular structure alone.

Retracted] DFT Based QSAR Study of Enzyme Ribonucleoside Diphosphate Reductase

Quantum chemical descriptors such as heat of formation, energy of HOMO, total energy, absolute hardness and chemical potential in different combinations have been used to develop QSAR models of inhibitors of enzyme ribonucleoside diphosphate reductase, RDR. The inhibitors are mainly derivatives of 1‐formylisoquinoline thiosemicarbazone and 2‐formylpyridine thiosemicarbazone. The values of various descriptors have been evaluated with the help of Win MOPAC 7.21 software using DFT method. Multiple linear regression analysis has been made with the help of above mentioned descriptors using the same software. Regression equations have been found to be successful models as indicated by the regression coefficient r2 having the value as high as 0.96 and cross validation coefficient rCV2 having the value approaching 0.95. The value of these two coefficients is indicative of high order of reliability for the proposed prediction. The results obtained are also validated on account of the closeness of observed and predicted inhibitory activities. The best combination of descriptors is heat of formation, total energy and energy of HOMO. Thus the prediction of suitability of inhibitors of the enzyme RDR can be made with the help of the best regression equation.

Development of QSAR models for microsomal stability: identification of good and bad structural features for rat, human and mouse microsomal stability

High throughput microsomal stability assays have been widely implemented in drug discovery and many companies have accumulated experimental measurements for thousands of compounds. Such datasets have been used to develop in silico models to predict metabolic stability and guide the selection of promising candidates for synthesis. This approach has proven most effective when selecting compounds from proposed virtual libraries prior to synthesis. However, these models are not easily interpretable at the structural level, and thus provide little insight to guide traditional synthetic efforts. We have developed global classification models of rat, mouse and human liver microsomal stability using in-house data. These models were built with FCFP_6 fingerprints using a Naïve Bayesian classifier within Pipeline Pilot. The test sets were correctly classified as stable or unstable with satisfying accuracies of 78, 77 and 75% for rat, human and mouse models, respectively. The prediction confidence was assigned using the Bayesian score to assess the applicability of the models. Using the resulting models, we developed a novel data mining strategy to identify structural features associated with good and bad microsomal stability. We also used this approach to identify structural features which are good for one species but bad for another. With these findings, the structure-metabolism relationships are likely to be understood faster and earlier in drug discovery.

QSAR study on N- (Aryl)-4-(Azolylethyl) Thiazole-5-Carboxamides: Novel Potent Inhibitors of VEGF Receptors I and II

QSAR study on N-(Aryl)-4-(azolylethyl) thiazole-5-carboxamides analogues, which are novel potent inhibitor of VEGF receptor II and I, were performed using topological, electronic and physicochemical descriptors. The results obtained demonstrate in detail, which specify that topological descriptors of the compounds play a significant role in developing QSAR models. The significance of presence and absence of substituents on particular position is successfully explored with the help of indicator variables. The results are critically discussed on the basis of multiple linear regression parameters.

Relationship Between Structure and Permeability in Artificial Membranes: Theoretical Whole Molecule Descriptors in Development of QSAR Models

AbstractThe relationships between structure and passive permeability in artificial membranes were studied using a structurally diverse data set of 60 compounds. The potential of whole molecule descriptors in the development of QSAR models was explored and the respective five‐parameter model is presented for the modeling of permeability. The presented QSAR model is validated internally and externally. Descriptors in the model include the hydrogen bonding ability which is solely connected with water solubility, hence hydrophilicity. In addition, the charge distribution, polarizability, and shape of molecules are also described by the descriptors. Insight is given into the structural characteristics that determine the passive mechanism of permeability.

Docking and 3D-QSAR Studies on Isatin Sulfonamide Analogues as Caspase-3 Inhibitors

To provide insight of their inhibition mechanism and facilitate the design of more potent ligands, a series of 59 isatin sulfonamide analogues were docked to the X-ray structure of caspase-3, one of the important cysteine aspartyl-specific execution proteases in apoptosis, and their binding conformations were analyzed by 3D-QSAR studies. Comparative molecular field analysis (CoMFA) and comparative molecular similarity index analysis (CoMSIA) studies suggest that both steric and electrostatic interactions contribute to the compounds' binding affinity, with the major contribution arising from hydrophobic interactions. The models show excellent correlation and high predictive power even evaluated by the most stringent criteria for a QSAR model. The results of this work demonstrate that structure-based design methods (such as docking) cultivate the development of reliable QSAR models; they also illustrate the utility of this procedure in design of new potent caspase-3 ligands.

Predictive models, based on classification algorithms, for compounds potentially active as mitochondrial ATP-sensitive potassium channel openers

Heart mitochondrial ATP-sensitive potassium channel (mito-K ATP channels) are deeply implicated in the self-defense mechanism of ischemic preconditioning. Therefore, exogenous molecules activating these channels are considered as a promising pharmacological tool to reduce the myocardial injury deriving from ischemia/reperfusion events. In our laboratory, a series of 4-spiro-substituted benzopyran derivatives were earlier synthesized and some of them exhibited anti-ischemic properties. In this study, the above compounds are exploited in order to develop QSAR models, based on classification approaches, capable of discriminating between the ones acting as cardioprotective agents and those that are unable to elicit such a property. Molecules belonging to the whole dataset were subjected to CODESSA and E-Dragon calculations in order to compute a large number of molecular descriptors enabling the construction of classification models. Based on the two program packages used, two different experiments were carried out, with the aim of identify batteries of models to be exploited for designing new cardioprotective agents from libraries of new chemical entities. Both model batteries satisfy the rigorous criteria adopted for the validation, either when tested on the training and test set, according to the most straightforward protocol, and when tested on an additional prediction set. They were proven to ensure successful applications in the field of cardioprotective agent design.